Free OpenRouter API
OpenRouter's :free model pool — dozens of open models at no cost, no card to start.
FreeLLMAPI is a free, open-source LLM API that routes across every provider with a real free tier. The OpenRouter models below are on the free tier of OpenRouter — reachable through one OpenAI-compatible key, with automatic failover when a provider hits its rate limit.
Free OpenRouter models (18)
| Model | Context | Free limits | Capabilities |
|---|---|---|---|
| qwen/qwen3-coder:free | 1.0M | 20 rpm, 50 rpd | tools |
| qwen/qwen3-next-80b-a3b-instruct:free | 262K | 20 rpm, 200 rpd | tools |
| openai/gpt-oss-120b:free | 131K | 20 rpm, 1000 rpd | tools |
| nvidia/nemotron-3-ultra-550b-a55b:free | 1M | 20 rpm, 200 rpd | tools |
| poolside/laguna-m.1:free | 131K | 20 rpm, 200 rpd | — |
| meta-llama/llama-3.3-70b-instruct:free | 131K | 20 rpm, 1000 rpd | tools |
| nousresearch/hermes-3-llama-3.1-405b:free | 131K | 20 rpm, 50 rpd | — |
| openai/gpt-oss-20b:free | 131K | 20 rpm, 200 rpd | tools |
| google/gemma-4-31b-it:free | 262K | 20 rpm, 200 rpd | — |
| google/gemma-4-26b-a4b-it:free | 262K | 20 rpm, 200 rpd | — |
| nvidia/nemotron-3-super-120b-a12b:free | 1M | 20 rpm, 200 rpd | tools |
| nvidia/nemotron-3-nano-30b-a3b:free | 262K | 20 rpm, 200 rpd | — |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 262K | 20 rpm, 200 rpd | — |
| cognitivecomputations/dolphin-mistral-24b-venice-edition:free | 33K | 20 rpm, 200 rpd | — |
| nvidia/nemotron-nano-9b-v2:free | 128K | 20 rpm, 200 rpd | — |
| liquid/lfm-2.5-1.2b-instruct:free | 33K | 20 rpm, 200 rpd | — |
| liquid/lfm-2.5-1.2b-thinking:free | 33K | 20 rpm, 200 rpd | — |
| meta-llama/llama-3.2-3b-instruct:free | 131K | 20 rpm, 200 rpd | — |
How to use OpenRouter for free
- Install FreeLLMAPI — the open-source router (GitHub). It runs locally and keeps your keys on your machine.
- Add a free key for OpenRouter on the Keys page — no credit card required.
- Point your OpenAI client at the local endpoint and pick a model:
from openai import OpenAI
# FreeLLMAPI runs locally; grab your unified key + endpoint on the Keys page.
client = OpenAI(base_url="http://localhost:3001/v1", api_key="freellmapi-...")
resp = client.chat.completions.create(
model="qwen/qwen3-coder:free",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ
Is the OpenRouter API really free?
Yes — these OpenRouter models run on genuine provider free tiers (on the free tier of OpenRouter). Inference costs nothing; you only add a free provider key.
Do I need a credit card?
No. The providers here offer free tiers that work without a card. You add the free key once and FreeLLMAPI routes to it.
How do I call OpenRouter through FreeLLMAPI?
Install the open-source router, add the provider's free key on the Keys page, then point any OpenAI SDK at your local endpoint — see the code sample above.